Study: Model Hallucinations Can Be Linearly Decoded

ziv_ravid · x · 2026-07-04

Researchers found that a model's state of "running on imagined content" might be linearly decodable, meaning it can theoretically be detected. The author notes that grounding without imagination is a camera, imagination without grounding is a mirage, and the truly interesting part lies at the seam between the two.

Original post →

More from Research

Research channel →